Task Fingerprinting for Meta Learning in Biomedical Image Analysis

  title={Task Fingerprinting for Meta Learning in Biomedical Image Analysis},
  author={Patrick Godau and Lena Maier-Hein},
Shortage of annotated data is one of the greatest bottlenecks in biomedical image analysis. Meta learning studies how learning systems can increase in efficiency through experience and could thus evolve as an important concept to overcome data sparsity. However, the core capability of meta learning-based approaches is the identification of similar previous tasks given a new task a challenge largely unexplored in the biomedical imaging domain. In this paper, we address the problem of quantifying… 

Figures and Tables from this paper


Exploring the Similarity of Medical Imaging Classification Problems
This paper investigates the first step of meta-learning – predicting which methods will perform well in an unseen classification problem, given previous experience with other classification problems, and investigates how to quantify the similarity of different classification problems.
Cats or CAT scans: transfer learning from natural or medical image source datasets?
  • V. Cheplygina
  • Computer Science, Physics
    Current Opinion in Biomedical Engineering
  • 2019
Transfusion: Understanding Transfer Learning for Medical Imaging
Investigating the learned representations and features finds that some of the differences from transfer learning are due to the over-parametrization of standard models rather than sophisticated feature reuse, and isolate where useful feature reuse occurs, and outline the implications for more efficient model exploration.
Exploiting the potential of unlabeled endoscopic video data with self-supervised learning
The proposed re-colorization of medical images with a conditional generative adversarial network (cGAN)-based architecture as auxiliary task can be used to radically reduce the manual annotation effort involved in training CNNs.
Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation
A deep stacked transformation approach for domain generalization that can be generalized to the design of highly robust deep segmentation models for clinical deployment and reaches the performance of state-of theart fully supervised models that are trained and tested on their source domains.
HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy
The HyperKvasir dataset is presented, the largest image and video dataset of the gastrointestinal tract available today and can play a valuable role in developing better algorithms and computer-assisted examination systems not only for gastro- and colonoscopy, but also for other fields in medicine.
Can Masses of Non-Experts Train Highly Accurate Image Classifiers? - A Crowdsourcing Approach to Instrument Segmentation in Laparoscopic Images
This study suggests that segmentations computed from annotations of multiple anonymous non-experts are comparable to those made by medical experts and that the scientific community might no longer need to rely on experts to generate reference or training data for certain applications.
Lapgyn4: a dataset for 4 automatic content analysis problems in the domain of laparoscopic gynecology
Four datasets extracted from gynecologic, laparoscopic interventions are published with the intend on encouraging research in the field of post-surgical automatic media analysis, designed with the following use cases in mind: medical image retrieval based on a query image, detection of instrument counts, surgical actions and anatomical structures.
The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions
The HAM10000 (“Human Against Machine with 10000 training images”) dataset is released, which consists of 10015 dermatoscopic images which are released as a training set for academic machine learning purposes and are publicly available through the ISIC archive.